Busca avançada
Ano de início
Entree
(Referência obtida automaticamente do Web of Science, por meio da informação sobre o financiamento pela FAPESP e o número do processo correspondente, incluída na publicação pelos autores.)

ast Resource and Timing Aware Design Optimisation for High-Level Synthesi

Texto completo
Autor(es):
Perina, Andre B. [1] ; Silitonga, Arthur [2] ; Becker, Jurgen [2] ; Bonato, Vanderlei [1]
Número total de Autores: 4
Afiliação do(s) autor(es):
[1] Univ Sao Paulo, BR-13566590 Sao Carlos, SP - Brazil
[2] Karlsruhe Inst Technol, D-76131 Karlsruhe - Germany
Número total de Afiliações: 2
Tipo de documento: Artigo Científico
Fonte: IEEE TRANSACTIONS ON COMPUTERS; v. 70, n. 12, p. 2070-2082, DEC 1 2021.
Citações Web of Science: 0
Resumo

Field-Programmable Gate Arrays (FPGA) are often present in energy-efficient systems, although its non-trivial development flow is an obstacle for massive adoption. High-Level Synthesis (HLS) approaches attempt to mitigate the gap by targetting FPGAs from software languages, however manual tuning is still essential to meet performance demands. We present a high-level design space exploration framework with timing and resource awareness that uses an estimator named Lina to evaluate each design point. Lina is a profiling-based approach that avoids the costly static analyses performed by HLS compilers, allowing a significantly faster exploration of optimisations. Estimations are improved by supporting a continuous range of operating frequencies and by considering resource usage for both floating-point and integer datapaths. For a given set of C kernels, the estimated solutions are among the best 1% for execution time and resource footprint. The exploration of each kernel using Lina was performed on average two orders of magnitude faster than using early HLS compiler reports, and four orders of magnitude faster than fully compiling each design point. By considering the design spaces traversed, our solutions reached 70% of the maximum speed-up achievable. This represents an average speed-up of 14-16x compared to the baseline designs with no optimisations enabled. (AU)

Processo FAPESP: 18/22289-6 - Ferramenta de mapeamento em alto-nível para arquiteturas heterogêneas com FPGAs e GPUs
Beneficiário:Andre Bannwart Perina
Linha de fomento: Bolsas no Exterior - Estágio de Pesquisa - Doutorado Direto
Processo FAPESP: 16/18937-7 - Ferramenta para exploração do espaço de projeto para arquiteturas heterogêneas de FPGAs e GPUs com foco em consumo de energia
Beneficiário:Andre Bannwart Perina
Linha de fomento: Bolsas no Brasil - Doutorado Direto